Improving Compositional Generalization in Semantic Parsing
This work addresses compositional generalization for semantic parsing, which is incremental as it builds on existing methods to improve a known bottleneck.
The paper tackled the problem of compositional generalization in semantic parsing by analyzing various models and proposing extensions to the attention module, resulting in a substantial reduction in the gap between in-distribution and out-of-distribution performance, though OOD performance remained lower.
Generalization of models to out-of-distribution (OOD) data has captured tremendous attention recently. Specifically, compositional generalization, i.e., whether a model generalizes to new structures built of components observed during training, has sparked substantial interest. In this work, we investigate compositional generalization in semantic parsing, a natural test-bed for compositional generalization, as output programs are constructed from sub-components. We analyze a wide variety of models and propose multiple extensions to the attention module of the semantic parser, aiming to improve compositional generalization. We find that the following factors improve compositional generalization: (a) using contextual representations, such as ELMo and BERT, (b) informing the decoder what input tokens have previously been attended to, (c) training the decoder attention to agree with pre-computed token alignments, and (d) downsampling examples corresponding to frequent program templates. While we substantially reduce the gap between in-distribution and OOD generalization, performance on OOD compositions is still substantially lower.